Tuhoiisa
Üstün
- Katılım
- 12 Ocak 2024
- Mesajlar
- 1.194
- Çözümler
- 20
- Beğeniler
- 749
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
Kod:
./llama-server \
-m "Hermes3.6-35B-A3B-Uncensored-Genesis-Final-APEX.gguf" \
--fit off \
--n-gpu-layers 999 \
--n-cpu-moe 17 \
--ctx-size 32768 \
--flash-attn on \
--jinja \
--host 127.0.0.1 \
--port 8080 \
--load-mode dio \
--cont-batching \
--cache-prompt \
--metrics \
--webui \
--warmup \
-b 4096 \
-ub 512
